© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10525
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating exceptions or exclusions within a sentence

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ento
    -0.81
    sonian
    -0.77
    eatured
    -0.76
    urred
    -0.76
    enth
    -0.76
    ierce
    -0.73
    accompan
    -0.73
    front
    -0.72
    orthy
    -0.72
    answered
    -0.71
    POSITIVE LOGITS
     occasional
    1.43
     maybe
    1.15
     perhaps
    1.04
     possibly
    0.91
     occasionally
    0.89
     minor
    0.84
     those
    0.82
     sporadic
    0.81
     one
    0.81
     briefly
    0.81
    Activations Density 0.106%

    No Known Activations